Advertisement

Ultrasound-Based Characterization of Prostate Cancer: An in vivo Clinical Feasibility Study

  • Farhad Imani
  • Purang Abolmaesumi
  • Eli Gibson
  • Amir Khojaste
  • Mena Gaed
  • Madeleine Moussa
  • Jose A. Gomez
  • Cesare Romagnoli
  • D. Robert Siemens
  • Michael Leviridge
  • Silvia Chang
  • Aaron Fenster
  • Aaron D. Ward
  • Parvin Mousavi
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8150)

Abstract

This paper presents the results of an in vivo clinical study to accurately characterize prostate cancer using new features of ultrasound RF time series. Methods: The mean central frequency and wavelet features of ultrasound RF time series from seven patients are used along with an elaborate framework of ultrasound to histology registration to identify and verify cancer in prostate tissue regions as small as 1.7 mm × 1.7 mm. Results: In a leave-one-patient-out cross-validation strategy, an average classification accuracy of 76% and the area under ROC curve of 0.83 are achieved using two proposed RF time series features. The results statistically significantly outperform those achieved by previously reported features in the literature. The proposed features show the clinical relevance of RF time series for in vivo characterization of cancer.

Keywords

RF time series tissue characterization prostate cancer 

References

  1. 1.
    Hodge, A.C., Fenster, A., Downey, D.B., Ladak, H.M.: Prostate boundary segmentation from ultrasound images using 2D active shape models: Optimisation and extension to 3D. Comput. Methods Programs Biomed. 84, 99–113 (2006)CrossRefGoogle Scholar
  2. 2.
    Inahara, M., Suzuki, H., Nakamachi, H., et al.: Clinical evaluation of transrectal power doppler imaging in the detection of PCa. Int. Urol. Neph. 36, 175–180 (2004)CrossRefGoogle Scholar
  3. 3.
    Han, S.M., Lee, H.J., Choi, J.U.: Computer-aided PCa detection using texture features and clinical features in ultrasound image. Digit. Imaging 21, 121–133 (2008)CrossRefGoogle Scholar
  4. 4.
    Tsui, P.H., Chang, C.C.: Imaging local scatterer concentrations by the Nakagami statistical model. Ultrasound Med. Biol. 33, 608–619 (2007)CrossRefGoogle Scholar
  5. 5.
    Feleppa, E., Porter, C., Ketterling, J., et al.: Recent developments in tissue-type imaging for planning and monitoring treatment of PCa. US Img. 26, 163–172 (2004)Google Scholar
  6. 6.
    Schmitz, G., Ermert, H., Senge, T.: Tissue-characterization of the prostate using RF ultrasonic signals. IEEE Trans. Ultrason. Ferr. Freq. Control 46, 126–138 (1999)CrossRefGoogle Scholar
  7. 7.
    Salcudean, S.E., French, D., Bachmann, S., Zahiri-Azar, R., Wen, X., Morris, W.J.: Viscoelasticity modeling of the prostate region using vibro-elastography. In: Larsen, R., Nielsen, M., Sporring, J. (eds.) MICCAI 2006. LNCS, vol. 4190, pp. 389–396. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  8. 8.
    Zhai, L., Madden, J., Foo, W.C., et al.: Acoustic radiation force impulse imaging of human prostates ex vivo. Ultrasound Med. Biol. 36, 576–588 (2010)CrossRefGoogle Scholar
  9. 9.
    Moradi, M., Abolmaesumi, P., Siemens, R., et al.: Augmenting detection of PCa in transrectal US images using SVM and RF TS. IEEE TBME 56, 2214–2224 (2009)Google Scholar
  10. 10.
    Moradi, M., Mahdavi, S., Nir, G., et al.: US RF time series for tissue typing: first in-vivo clinical results. In: SPIE (2013)Google Scholar
  11. 11.
    Gibson, E., Crukley, C., Gaed, M., et al.: Registration of prostate histology images to ex vivo MR images via strand-shaped fiducials. JMRI 36, 1402–1412 (2012)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Farhad Imani
    • 1
  • Purang Abolmaesumi
    • 2
  • Eli Gibson
    • 3
  • Amir Khojaste
    • 1
  • Mena Gaed
    • 3
  • Madeleine Moussa
    • 4
  • Jose A. Gomez
    • 4
  • Cesare Romagnoli
    • 3
  • D. Robert Siemens
    • 5
  • Michael Leviridge
    • 5
  • Silvia Chang
    • 6
  • Aaron Fenster
    • 3
  • Aaron D. Ward
    • 3
  • Parvin Mousavi
    • 1
  1. 1.Queen’s UniversityKingstonCanada
  2. 2.The University of British ColumbiaVancouverCanada
  3. 3.University of Western OntarioLondonCanada
  4. 4.London Health Science CentreLondonCanada
  5. 5.Kingston General HospitalKingstonCanada
  6. 6.Vancouver General HospitalVancouverCanada

Personalised recommendations